© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52759
    Prev
    Next
    INDEX
    Explanations

    private [context]

    np_acts-logits-general · gemini-2.5-flash-lite

    private company, service, or entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bakın
    0.48
     অব
    0.48
    膑
    0.48
     สิน
    0.47
     IMPORT
    0.46
    }/>
    0.45
     EFFECT
    0.45
    ICK
    0.44
     Об
    0.44
     時
    0.43
    POSITIVE LOGITS
    private
    1.43
     private
    1.39
    Private
    1.38
     Private
    1.34
    PRIVATE
    1.33
     प्राइवेट
    1.33
     privada
    1.25
     PRIVATE
    1.23
     privati
    1.23
     निजी
    1.21
    Activations Density 0.035%

    No Known Activations